@thecodingwhale/cv-processor/dist/extractors/TextExtractor.d.ts

CV Processor to extract structured data from PDF resumes using TypeScript

/**
 * Class for extracting text from PDF documents
 */
export declare class TextExtractor {
    /**
     * Extract text from a PDF file, with OCR fallback if needed
     */
    extractTextFromPDF(pdfPath: string): Promise<string>;
    /**
     * Extract text using OCR with Tesseract.js
     * Note: This is a simplified implementation as converting PDF pages to images
     * is more complex in Node.js than in Python
     */
    private extractTextWithOCR;
}